fee9b9acb1
Separate ASR (2 workers) from summary/RAG post-processing, add LightRAG chat API, batch upload fixes, and local model mounts for Docker deployment. Co-authored-by: Cursor <cursoragent@cursor.com>
15 lines
198 B
Plaintext
15 lines
198 B
Plaintext
fastapi
|
|
uvicorn[standard]
|
|
python-multipart
|
|
websockets
|
|
python-docx
|
|
pyyaml
|
|
whisperx
|
|
|
|
# RAG / LightRAG
|
|
lightrag-hku>=1.4.0
|
|
openai>=1.0.0
|
|
python-dotenv>=1.0.0
|
|
sentence-transformers>=3.0.0
|
|
numpy>=1.24.0
|